Skip to main content
Glama
AlmaLinux

albs-mcp

Official
by AlmaLinux

search_log

Find the root cause of a build failure by searching the log for error signatures or a regex, returning matches with context. Use when tail only shows the symptom.

Instructions

Find the failure in a build log: grep it and return each hit with context.

START HERE when investigating a failed build — do not read tails first. In a parallel make -j log the real compile error sits hundreds of lines above the end, so the tail shows only make: *** Error 2: the symptom, not the cause. This finds the cause in one call.

pattern is a Python regex; omit it to use the built-in build-failure signatures (compiler/link errors, failed patch hunks, unresolved BuildRequires, RPM packaging errors, %check failures, OOM/network trouble). Matched lines are prefixed >>> and every line is numbered, so a hit's number can be fed straight to read_log_range to see more.

Only the first max_matches hits are reported — the first error is the root cause and the rest are cascades — but the header counts all of them. Lines are clipped to max_line_chars around the match (0 = verbatim, needed when quoting an exact multi-KB command line). The log is downloaded automatically if not already on disk.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
afterNo
beforeNo
patternNo
build_idYes
filenameYes
max_charsNo
max_matchesNo
max_line_charsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are absent, so the description carries the full burden of behavioral disclosure. It reveals that only the first max_matches hits are returned (while the header counts all), that lines are clipped per max_line_chars, that the log is auto-downloaded, and that a default pattern set is used when pattern is omitted. These are concrete behavioral traits beyond the schema, with no contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, followed by a concise rationale and then parameter-specific behaviors. Every sentence contributes—whether distinguishing from siblings, explaining the root-cause logic, or detailing output formatting. There is no filler, and the structure makes scanning easy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 8 parameters, no annotations, and an output schema (which shifts return-detail responsibility), the description is remarkably complete. It covers the primary use case, explains why this tool is the correct entry point, details the output format (>>> prefix and line numbers), and provides sibling routing. No critical information an agent needs to call this tool correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It explains the meaning and behavior of pattern (with defaults), max_matches (first N hits only), and max_line_chars (clipping, including 0=verbatim). It implies before/after provide context but does not explicitly describe them. This leaves a small gap, but the most decision-relevant parameters are covered, and the description adds substantial value over the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Find the failure in a build log: grep it and return each hit with context.' It explicitly distinguishes itself from siblings with 'START HERE when investigating a failed build — do not read tails first' and explains why, setting it apart from read_log_tail. This is a clear, precise purpose that an agent can act on without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance: 'START HERE when investigating a failed build' and advises against reading tails first. It also names the alternative tool (read_log_range) for drilling into a specific hit, and explains why this tool is the right first step. This is complete usage routing with no reliance on inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AlmaLinux/albs-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server